Skip to main content
Journal cover image

Perceptron error surface analysis: a case study in breast cancer diagnosis.

Publication ,  Journal Article
Markey, MK; Lo, JY; Vargas-Voracek, R; Tourassi, GD; Floyd, CE
Published in: Comput Biol Med
March 2002

Perceptrons are typically trained to minimize mean square error (MSE). In computer-aided diagnosis (CAD), model performance is usually evaluated according to other more clinically relevant measures. The purpose of this study was to investigate the relationship between MSE and the area (A(z)) under the receiver operating characteristic (ROC) curve and the high-sensitivity partial ROC area ((0.90)A'(z)). A perceptron was used to predict lesion malignancy based on two mammographic findings and patient age. For each performance measure, the error surface in weight space was visualized. Comparison of the surfaces indicated that minimizing MSE tended to maximize A(z), but not (0.90)A'(z).

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Comput Biol Med

DOI

ISSN

0010-4825

Publication Date

March 2002

Volume

32

Issue

2

Start / End Page

99 / 109

Location

United States

Related Subject Headings

  • Neural Networks, Computer
  • Mammography
  • Humans
  • Female
  • Diagnostic Errors
  • Diagnosis, Differential
  • Diagnosis, Computer-Assisted
  • Breast Neoplasms
  • Breast
  • Biomedical Engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Markey, M. K., Lo, J. Y., Vargas-Voracek, R., Tourassi, G. D., & Floyd, C. E. (2002). Perceptron error surface analysis: a case study in breast cancer diagnosis. Comput Biol Med, 32(2), 99–109. https://doi.org/10.1016/s0010-4825(01)00035-x
Markey, Mia K., Joseph Y. Lo, Rene Vargas-Voracek, Georgia D. Tourassi, and Carey E. Floyd. “Perceptron error surface analysis: a case study in breast cancer diagnosis.Comput Biol Med 32, no. 2 (March 2002): 99–109. https://doi.org/10.1016/s0010-4825(01)00035-x.
Markey MK, Lo JY, Vargas-Voracek R, Tourassi GD, Floyd CE. Perceptron error surface analysis: a case study in breast cancer diagnosis. Comput Biol Med. 2002 Mar;32(2):99–109.
Markey, Mia K., et al. “Perceptron error surface analysis: a case study in breast cancer diagnosis.Comput Biol Med, vol. 32, no. 2, Mar. 2002, pp. 99–109. Pubmed, doi:10.1016/s0010-4825(01)00035-x.
Markey MK, Lo JY, Vargas-Voracek R, Tourassi GD, Floyd CE. Perceptron error surface analysis: a case study in breast cancer diagnosis. Comput Biol Med. 2002 Mar;32(2):99–109.
Journal cover image

Published In

Comput Biol Med

DOI

ISSN

0010-4825

Publication Date

March 2002

Volume

32

Issue

2

Start / End Page

99 / 109

Location

United States

Related Subject Headings

  • Neural Networks, Computer
  • Mammography
  • Humans
  • Female
  • Diagnostic Errors
  • Diagnosis, Differential
  • Diagnosis, Computer-Assisted
  • Breast Neoplasms
  • Breast
  • Biomedical Engineering